© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17442
    Prev
    Next
    INDEX
    Explanations

    references to time management and allocation

    oai_token-act-pair · gpt-3.5-turbo

    references to time management and productivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gors
    -1.08
     Breed
    -0.85
     pedigree
    -0.81
     Frankenstein
    -0.78
     Mk
    -0.78
     deform
    -0.76
    DNA
    -0.76
     indemn
    -0.76
     Chev
    -0.73
    çīĪ
    -0.72
    POSITIVE LOGITS
     distractions
    1.37
     leisure
    1.33
     multit
    1.30
     evenings
    1.21
     distraction
    1.20
     waking
    1.19
     downtime
    1.18
     mornings
    1.16
     sleep
    1.16
    entary
    1.15
    Activations Density 0.819%

    No Known Activations